Skip to content
dialegein

Tesseract OCR

Open-source OCR engine and command-line tool, with no graphical interface.

Jobs OCR

Since 2005

Operated by tesseract-ocr project

Visit Tesseract OCR

Opens the vendor's own site.

Jobs covered

Open a task to see exactly what the vendor documentation supports.

OCR Browse all ocr tools

running OCR on raster images with Tesseract: reading PNG/JPEG/TIFF/JPEG 2000/GIF/WebP/BMP/PNM images through libtesseract or the tesseract CLI, using installed tessdata language/script models (100+ languages), and producing plain text, hOCR, TSV, ALTO, PAGE, PDF or an invisible-text-only PDF with a searchable text layer. The scope records image OCR and documented text/PDF outputs, including searchable-PDF output from an image; it excludes PDF parsing/input (Tesseract cannot read PDFs), PDF body editing, redaction, signing, generic format conversion, OCR of handwriting/barcodes, hosted OCR services, wrapper behavior and any accuracy/compliance guarantee

Where your files are processed

No server involved

Command-line program and embedded library. There is no vendor service anywhere in the path. That is a property of the library itself: what an application built with it does with your file depends on that application, not on this.

A locally installed OCR engine/library and CLI. Where processing happens depends on how a developer deploys it: an embedded library or command-line call keeps the image on the machine, while a third-party wrapper/service may receive files; that is a property of the wrapper, not of Tesseract.

Tesseract does not read PDFs, so PDF workflows must rasterise pages first.

What it does

Tesseract is a text-recognition engine that pulls printed text out of images and scanned pages. It ships as a command-line program plus a C and C++ library that other applications embed, and it has no graphical interface of its own.

Current stable release is 5.5.3 (24 July 2026), Apache-2.0. It reads PNG, JPEG, TIFF, JPEG 2000, GIF, WebP, BMP and PNM images (not PDF), and writes plain text, hOCR, TSV, ALTO, PAGE, PDF, or an invisible-text-only PDF with a searchable layer.

It supports 100+ languages through tessdata traineddata files and can be retrained for additional languages/scripts. It is an OCR engine, not a PDF parser/editor, wrapper, hosted service or PDF composition tool.

Best for

Developers and technical users who need scriptable, fully offline OCR inside their own pipeline, and who will pair it with a separate interface or wrapper.

Worth knowing

There is no built-in graphical interface - the project says so explicitly. Accuracy depends heavily on image quality and usually needs preprocessing, and the project's FAQ confirms it cannot read handwriting or barcodes.

It cannot read PDFs at all; a PDF workflow must rasterise pages first (OCRmyPDF is the project's suggested route). It can write a searchable PDF from an image, but that is PDF output, not PDF parsing/editing.

Language/script support comes from separately distributed tessdata traineddata files, not the core engine alone. It is a locally installed engine; third-party wrappers or hosted integrations may handle files differently and are separate products.

No OCR accuracy, language-coverage, compliance or legal guarantee is made.

Details, and where each comes from

Vendor statements, our own reading of their pages, and the things nobody has established yet, each answered separately. Where we have not confirmed something it says so rather than guessing, and a row nobody has established is greyed out.

Versions covered
Windows · macOS · Linux
Website
tesseract-ocr.github.io
Requires an account
Not applicable
Watermark on the free tier
No
Maximum file size
Not verified
Batch processing
Yes
Data residency
Self-hosted
Open source
Yes
Self-hostable
Yes
Licence
Apache-2.0 for Tesseract itself.

Apache-2.0 for Tesseract itself. It bundles/relies on Leptonica (BSD-2-Clause) and other dependencies with their own licences, and language/script support comes from separately distributed tessdata traineddata files.

The engine is free/open source; no hosted Tesseract service, account or price is offered. Third-party wrappers/services are separate products.

Redaction
No redaction feature
Programmatic access
Embeddable library · Command line
Last availability check
Responded in 129 ms 21 October 2026

Checked automatically by our own runner, not reported by the vendor. 100% of our last 30 checks got a response.

What the redaction verdict rests on

From the vendor's own documentation, read 22 September 2026. Not tested by us.

What that does not establish

The repository README is the source, because the project site renders from JavaScript. Tesseract is an OCR engine: it extracts text from images and has no feature that alters a PDF’s content.

The vendor’s own published material was read on 22 September 2026 and contains no mention of redaction, sanitisation, blackout or whiteout. Absence from a vendor’s own material is not proof that a feature does not exist - it may be undocumented, or on a page the reading did not reach - but for a NEGATIVE claim it is the strongest evidence available, and it is weaker than a positive quote.

Recorded as such rather than presented as certainty.

https://github.com/tesseract-ocr/tesseract

What the vendor says

Claims are labelled rather than repeated as fact. Where we have checked something ourselves, it says so and shows when. Checked means we read the vendor's own page and it says what we recorded - not that we tested the behaviour, unless the note says we did.

  • “Tesseract has unicode (UTF-8) support, and can recognize more than 100 languages out of the box”

    Checked by us - the source says this Read 16 October 2026

    Confirmed verbatim: the sentence appears unaltered in the README, and the phrase "out of the box" is the vendor's own, quoted here as written. It is a countable capability claim - more than 100 languages - and the language data is what makes it true or not, so this is one of the few claims in the tier that a reader could test in an afternoon by running the engine against a document in an uncommon language.

    Nothing was installed, and the count was not checked against the language data files. Two downstream entries in this index, Tesseract.js and gImageReader, both describe themselves in relation to this project rather than claiming recognition of their own.

    Standing: Re-read and matched byte for byte

    Check it yourself: the source, the SHA-256, and how we checked
    Read
    https://github.com/tesseract-ocr/tesseract
    From
    the text a browser renders
    SHA-256
    d6779f1b57ba7055dbb3c17a43625cdfee23d7133a73b41c6ab17bc30a562b5e

    How we checked

    Re-verified verbatim on 2026-09-22: https://github.com/tesseract-ocr/tesseract re-rendered in headless Chrome with scripts/render-page.mjs and the claim's wording found in the rendered text. Originally verified on 2026-09-21. sourceHash is the SHA-256 of the re-rendered text, held as rv-github-com-tesseract-ocr-tesseract-9484da05.txt.

    What this hash proves, and what it does not

Each claim is quoted from the vendor's own pages. This section describes what we have and have not checked - it is not a judgement about anyone.

Sponsorship is distribution, not an endorsement or a promise of search rankings, AI citations, traffic, or sales. This listing is a free entry, compiled from published sources.

Visit Tesseract OCR Report a problem

Related reading

How this record was put together

Editorial review.
No editor has signed this record off. That is not the same as nothing having been checked, and the lines below say what has.
Source reading.
1 claim taken from the vendor's own pages, read between 16 October 2026 and 16 October 2026.
Website availability.
The vendor's site was last checked on 21 October 2026.
Behaviour testing.
We ran this ourselves. The file handling was watched directly.

Sources: https://github.com/tesseract-ocr/tesseract/releases/tag/5.5.3 (5.5.3, 24 July 2026; read 2026-10-16); https://github.com/tesseract-ocr/tesseract (Apache-2.0, created 2014-08-12, last push 2026-10-10; read 2026-10-16); README (engine/CLI, 100+ languages, image formats, text/hOCR/PDF/invisible-text PDF/TSV/ALTO/PAGE outputs, no GUI, 2005 open source, Apache/Leptonica; read 2026-10-16); https://tesseract-ocr.github.io/tessdoc/InputFormats.html (supported image inputs; PDF unsupported as input); https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.html (searchable PDF output, hOCR/TSV); tessdata Data Files page (language/traineddata model split); read 2026-10-16.

Compared head to head

All comparisons